youtube.video_comments
Fetch top-level comments for a public YouTube video by its 11-character video id. Returns comment text, author summary, vote and reply counts, pinned status, total comment count, and cursorNext for the next page. Use sort_by to choose comment order: - sort_by: Top comments, Newest first Sort valu...
This record as markdown: /tools/io-github-vee3io-vee3/youtube.video-comments.md
What youtube.video_comments does on Vee3
AI agents call youtube.video_comments to retrieve information from Vee3 without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
cursor | object | — | Pagination cursor from a previous response cursorNext field. |
sort_by | object | — | Comment sort order. One of: Top comments, Newest first. |
video_id | string | Yes | YouTube video id (11 characters, not a URL). |
Parameters from the server's own tool schema.
Why youtube.video_comments is rated Low
This is a straightforward data retrieval tool with no side effects. It queries publicly available YouTube comments and returns metadata. There is no risk of data modification, deletion, financial impact, or code execution. Even in agent misuse scenarios, the worst outcome would be excessive API calls or privacy concerns from comment aggregation, which represent low severity.
From the tool's definition Tool fetches and retrieves comment data from public YouTube videos—'Fetch top-level comments' and 'Returns comment text, author summary, vote and reply counts'. No creation, modification, deletion, or execution of external operations. Data retrieval only.
Attacks that exploit this kind of access
The rule that runs youtube.video_comments safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Vee3, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For youtube.video_comments, this is the rule to start with:
youtube.video_comments is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Vee3, apply this rule, and every youtube.video_comments call is checked against it from then on.
Questions about youtube.video_comments
Fetch top-level comments for a public YouTube video by its 11-character video id. Returns comment text, author summary, vote and reply counts, pinned status, total comment count, and cursorNext for the next page. Use sort_by to choose comment order: - sort_by: Top comments, Newest first Sort values are matched case-insensitively. Use cursor with the same video_id to paginate: pass cursorNext from a prior response. sort_by and cursor cannot be combined. Cost = 15 tokens. It is categorised as a Read tool in the Vee3 MCP Server, which means it retrieves data without modifying state.
youtube.video_comments accepts 3 parameters: cursor, sort_by, video_id. Required: video_id. The full parameter table on this page comes from the server's own tool schema.
Register the Vee3 MCP server in PolicyLayer and add a rule for youtube.video_comments: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Vee3. Nothing to install.
youtube.video_comments is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the youtube.video_comments rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for youtube.video_comments. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
youtube.video_comments is provided by the Vee3 MCP server (https://mcp.vee3.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vee3, and thousands of servers like it.
This server
Across the catalogue